FLUX 3 Video
FLUX 3 Video is a video generation model from Black Forest Labs that supports audio, keyframes, and video continuation.
Black Forest LabsText-to-video generation with audio and keyframes
FLUX 3 Video is a video generation model developed by Black Forest Labs, released in July 2026. It accepts text prompts alongside optional inputs such as keyframe images and a starting video clip, enabling both text-to-video generation and video continuation workflows. The model supports audio generation as a built-in toggle, making it possible to produce video with synchronized sound in a single request.
FLUX 3 Video is designed for use cases that require flexible output configuration, including selectable resolution, aspect ratio, and duration. A draft mode is available for faster, lower-cost previews before committing to a full render. Pricing is usage-based at $0.06–$0.53 per second of generated video, and the model is available directly through MindStudio without requiring a separate API key.
What FLUX 3 Video supports
Video Generation
Generates video clips from text prompts with configurable resolution, aspect ratio, and duration. Output length and quality are selectable at request time.
Audio Generation
Optionally produces synchronized audio alongside the generated video in a single request, toggled via the generate_audio parameter.
Keyframe Conditioning
Accepts one or more keyframe images as input to guide the visual content and composition of the generated video.
Video Continuation
Extends an existing video clip by accepting a start_video URL input, allowing seamless continuation from a prior generation or uploaded footage.
Draft Mode
A lower-fidelity rendering mode that reduces generation time and cost, useful for previewing output before a full-quality render.
Safety Controls
Exposes a numeric safety_tolerance parameter that lets developers adjust the strictness of content filtering applied to generated outputs.
Ready to build with FLUX 3 Video?
Get Started FreeCommon questions about FLUX 3 Video
How is FLUX 3 Video priced?
FLUX 3 Video is priced at $0.06–$0.53 per second of generated video. The exact cost depends on the selected resolution, duration, and whether draft mode is enabled.
What is the context window for FLUX 3 Video?
The model has a context window of 5,000 tokens, which applies to the text prompt describing the video content.
Can FLUX 3 Video extend an existing video clip?
Yes. The model accepts a start_video URL input that allows it to continue from an existing video clip, supporting video continuation workflows.
Does FLUX 3 Video generate audio?
Yes. Audio generation is an optional toggle (generate_audio) that can be enabled at request time to produce synchronized sound alongside the video output.
What resolutions and aspect ratios does FLUX 3 Video support?
Resolution and aspect ratio are both selectable inputs at request time. The specific available values are configurable through the toggleGroup and select controls exposed by the model.
When was FLUX 3 Video released?
FLUX 3 Video was released in July 2026 by Black Forest Labs.
Parameters & options
One image starts the clip, two pin start and end, or up to 10 frames as a storyboard.
The clip to continue from. FLUX 3 picks up from its final frames.
Duration in seconds, or auto to let the model decide.
Generate synchronized audio (dialogue, effects, ambience) alongside the video.
Generate a fast HD preview.
0 is strictest, 4 is most permissive. Default is 2.
Explore similar models
Black Forest LabsFLUX.2 [max]
FLUX.2 [max] is a flagship image generation model from Black Forest Labs that accepts source images and custom dimensions as input.
Black Forest LabsFLUX.2 [klein] 9B
FLUX.2 [klein] 9B is a 9-billion-parameter image generation model from Black Forest Labs released in January 2026.
Black Forest LabsFLUX.2 [turbo]
FLUX.2 [turbo] is a text-to-image generation model from Black Forest Labs designed for fast, high-quality image output.
ByteDanceSeedance 2.5 Turbo
Seedance 2.5 Turbo is a video generation model from ByteDance that supports text-to-video, image-to-video, and video editing modes.
WanWan 3.0
Wan 3.0 is a video generation model that converts text prompts and images into video clips with optional audio output.
GoogleGemini Omni Flash
Gemini Omni Flash is a video generation model from Google that supports image and video inputs with multimodal editing capabilities.
Start building with FLUX 3 Video
No API keys required. Create AI-powered workflows with FLUX 3 Video in minutes — free.